INDEX

Explanations

technical terms and specifications related to scientific experiments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mi

-0.13

ìļĶ

-0.13

Æ°á»¡ng

-0.13

abi

-0.13

ardin

-0.13

ense

-0.12

muz

-0.12

.SDK

-0.12

 MatTable

-0.12

 thÆ°

-0.12

POSITIVE LOGITS

eya

0.15

 NONINFRINGEMENT

0.15

Ã¡no

0.14

holder

0.14

_ALLOWED

0.13

hiba

0.13

.spy

0.13

avenport

0.13

 Unblock

0.13

-holder

0.13

Activations Density 0.042%

technical terms and specifications related to scientific experiments

No Comments

No Known Activations